corpus_explorer.py 文件源码

def visualize_topics(H):
    '''
    INPUT
         - H matrix of topics
    OUTPUT
         - a scatter plot of the relative location of the different topics
         from each other in a flattened space using PCA
         - color_list - the list of colors to be used in the next
         visualizations of the tweets
    Returns the color list
    '''
    mds = MDS(n_jobs=-1)
    # pca = PCA(n_components=2)
    # hflat = pca.fit_transform(H)
    hflat = mds.fit_transform(H)
    # colors = cm.rainbow(hflat.shape[0]-1)
    colors = cycle(["r", "b", "g", "c", "m", "y", "k", "w"])
    color_list = []
    for i, row in enumerate(hflat):
        color = next(colors)
        plt.scatter(row[0], row[1],
                    label='topic number {}'.format(i+1), color=color)
        color_list.append(color)
    plt.legend(loc='best')
    plt.show()
    return color_list, mds